End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Singh, Prachi, Ganapathy, Sriram
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916501954494464
author Singh, Prachi
Ganapathy, Sriram
author_facet Singh, Prachi
Ganapathy, Sriram
contents Speaker diarization, the task of segmenting an audio recording based on speaker identity, constitutes an important speech pre-processing step for several downstream applications.The conventional approach to diarization involves multiple steps of embedding extraction and clustering, which are often optimized in an isolated fashion. While end-to-end diarization systems attempt to learn a single model for the task, they are often cumbersome to train and require large supervised datasets. In this paper, we propose an end-to-end supervised hierarchical clustering algorithm based on graph neural networks (GNN), called End-to-end Supervised HierARchical Clustering (E-SHARC). The embedding extractor is initialized using a pre-trained x-vector model while the GNN model is trained initially using the x-vector embeddings from the pre-trained model. Finally, the E-SHARC model uses the front-end mel-filterbank features as input and jointly optimizes the embedding extractor and the GNN clustering module, performing representation learning, metric learning, and clustering with end-to-end optimization. Further, with additional inputs from an external overlap detector, the E-SHARC approach is capable of predicting the speakers in the overlapping speech regions. The experimental evaluation on benchmark datasets like AMI, Voxconverse and DISPLACE, illustrates that the proposed E-SHARC framework provides competitive diarization results using graph based clustering methods.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization
Singh, Prachi
Ganapathy, Sriram
Audio and Speech Processing
Artificial Intelligence
Sound
Speaker diarization, the task of segmenting an audio recording based on speaker identity, constitutes an important speech pre-processing step for several downstream applications.The conventional approach to diarization involves multiple steps of embedding extraction and clustering, which are often optimized in an isolated fashion. While end-to-end diarization systems attempt to learn a single model for the task, they are often cumbersome to train and require large supervised datasets. In this paper, we propose an end-to-end supervised hierarchical clustering algorithm based on graph neural networks (GNN), called End-to-end Supervised HierARchical Clustering (E-SHARC). The embedding extractor is initialized using a pre-trained x-vector model while the GNN model is trained initially using the x-vector embeddings from the pre-trained model. Finally, the E-SHARC model uses the front-end mel-filterbank features as input and jointly optimizes the embedding extractor and the GNN clustering module, performing representation learning, metric learning, and clustering with end-to-end optimization. Further, with additional inputs from an external overlap detector, the E-SHARC approach is capable of predicting the speakers in the overlapping speech regions. The experimental evaluation on benchmark datasets like AMI, Voxconverse and DISPLACE, illustrates that the proposed E-SHARC framework provides competitive diarization results using graph based clustering methods.
title End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2401.12850